code-buddy (phuetz/code-buddy) is an MCP server listed on the M8ven Trust Index. It scores 37 out of 100, grade F. It declares 9 tools. No publisher has claimed this listing.
Local-first AI coding agent for the terminal. 64 LLM providers, 30 of them free or local $0, with auto-failover. 220+ tools, a peer-to-peer fleet, and a desktop app. No API bill required.
Warning. Serious findings were identified. Review the full report before connecting. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.
How we verified
Verified is a snapshot. Live keeps it current, and builds your track record.
⚡ Connect GitHub → continuous verification on every pushwhy connect →Who stands behind it
phuetz
Source: github_repo_search
Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →
Install from
The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.
These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.
codebuddy_askAsk CodeBuddy AI a question and get a response
codebuddy_complete_codeGet AI code completion suggestions
fcs_executeExecute FCS (FileCommander Script) code
read_fileRead the contents of a file
write_fileWrite content to a file
list_directoryList files and directories in a path
search_contentSearch for text in files
git_statusGet git repository status
execute_shellExecute a shell command
agent_chatbehind configSend a message to the Code Buddy AI agent and get a response with tool call results. Use for conversational interactions.
agent_taskbehind configExecute an autonomous task using Code Buddy agent. For complex tasks, uses DAG-based planning; for simple tasks, processes directly. Returns all tool calls and results.
agent_planbehind configCreate an execution plan for a task without executing it. Returns the DAG-based task plan with dependencies.
ckg_recallbehind configckg_ingestbehind configdesktop_screenshotbehind configCapture a screenshot of the desktop (fullscreen by default, or a region). Returns the saved PNG path and dimensions. Read-only.
desktop_snapshotbehind configEnumerate on-screen UI elements (accessibility tree) with numeric refs, roles, labels, and click coordinates. Read-only. Use the returned coordinates with desktop_click.
desktop_clickbehind configClick the mouse at screen coordinates. Requires CODEBUDDY_MCP_DESKTOP_CONTROL=1. Actuates the real desktop.
desktop_move_mousebehind configMove the mouse cursor to screen coordinates. Requires CODEBUDDY_MCP_DESKTOP_CONTROL=1.
desktop_typebehind configType text at the current focus. Requires CODEBUDDY_MCP_DESKTOP_CONTROL=1. Actuates the real keyboard.
desktop_keybehind configPress a key (optionally with modifiers), e.g. "enter", "escape", "tab", "f5". Requires CODEBUDDY_MCP_DESKTOP_CONTROL=1.
memory_searchbehind configSearch Code Buddy's semantic memory for relevant stored knowledge, patterns, and context.
memory_savebehind configSave a piece of knowledge to Code Buddy's persistent memory for future reference.
session_listbehind configList recent Code Buddy chat sessions with their IDs, names, and timestamps.
session_resumebehind configResume a previous Code Buddy session by ID, restoring its chat history and context.
web_searchbehind configSearch the web using Code Buddy's configured search providers (Brave, Perplexity, DuckDuckGo, etc.).
Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.
Vitest: Path Traversal / Arbitrary File Read via @vitest/mocker Redirect Mock
A2A_BRIDGE_DEFAULT_AGENTA2A_BRIDGE_DEFAULT_MODELA2A_BRIDGE_DEFAULT_SKILLANTHROPIC_API_KEYANTHROPIC_MODELAUTH_ENABLEDCHATBOX_PORTCHATGPT_MODELCODEBUDDY_A2A_PUBLIC_URLCODEBUDDY_AUDIT_DIRCODEBUDDY_BUNDLED_SKILLS_DIRCODEBUDDY_CLICODEBUDDY_CLI_VERSIONCODEBUDDY_COGNITION_METRICS_EVERYCODEBUDDY_COGNITIVE_SPECIALISTSCODEBUDDY_COGNITIVE_SPECIALIST_MAX_PER_HOURCODEBUDDY_CONVERSATION_EVAL_COOLDOWN_MSCODEBUDDY_CONVERSATION_EVAL_EVERYCODEBUDDY_CONVERSATION_EVAL_MIN_STREAKCODEBUDDY_DISABLE_MCPCODEBUDDY_DREAM_EVERYCODEBUDDY_EPISODE_EVERYCODEBUDDY_FLEET_HOSTNAMECODEBUDDY_FLEET_MACHINE_LABELCODEBUDDY_FLEET_REPO_PATHCODEBUDDY_FLEET_TICK_INTERVAL_MSCODEBUDDY_HEADLESSCODEBUDDY_HEARTBEAT_EVERYCODEBUDDY_INNER_LIFE_EVERYCODEBUDDY_JOKES_TOPUP_EVERYCODEBUDDY_LISA_SELFIE_REFILL_EVERYCODEBUDDY_LLM_ORDERCODEBUDDY_LOCALECODEBUDDY_MCP_DESKTOP_CONTROLCODEBUDDY_MODEL_FALLBACK_WARNEDCODEBUDDY_PIPER_BINCODEBUDDY_PREFETCH_INTERVAL_MSCODEBUDDY_PROVIDERForce the local Ollama path (no API key).CODEBUDDY_QUIETCODEBUDDY_SCHEDULE_TICKS_EVERYCODEBUDDY_SELF_IMPROVE_PROPOSERCODEBUDDY_SENSORY_CAMERACODEBUDDY_SENSORY_SPEAK_CWDCODEBUDDY_SENSORY_SPEAK_FACT_MODELCODEBUDDY_SENSORY_SPEECHCODEBUDDY_SENSORY_TOKENCODEBUDDY_SERVER_CHANNEL_INTAKECODEBUDDY_SESSION_END_FLUSH_TIMEOUT_MSCODEBUDDY_SYSTEM_VITALS_EVERYCODEBUDDY_VOICE_IMPROVE_EVERYCODEBUDDY_VOICE_MODEL_REFRESH_MSCORS_ORIGINSGEMINI_API_KEYGEMINI_MODELGITHUB_ACTIONSGITHUB_TOKENGOOGLE_API_KEYGROK_API_KEYGROK_BASE_URLGROK_FORCE_TOOLSGROK_MODELGROK_SKIP_PERMISSIONSGROK_VIM_MODEHOSTJWT_EXPIRATIONJWT_SECRETRequired by the HTTP server in production.LMSTUDIO_HOSTLOGGINGLOG_LEVELMAX_COSTMAX_REQUEST_SIZEMCP_DEBUGMETRICS_CONSOLEMETRICS_FILEMETRICS_INTERVALMETRICS_PATHOLLAMA_HOSTOLLAMA_MODELOPENAI_API_KEYOPENAI_BASE_URLOPENAI_MODELPERF_TIMINGRATE_LIMIT_MAXRATE_LIMIT_WINDOWSECURITY_HEADERSWS_ENABLEDXAI_API_KEYYOLO_MODEFull autonomy with guardrails. Setting YOLO_MODE=true alone only warns; it does not arm it.BUDDY_SENSE_BRIDGE_URLBUDDY_SENSE_TOKENBUDDY_EAR_DEVICEBUDDY_EAR_RMS_ONBUDDY_EAR_RMS_OFFBUDDY_EAR_MIN_MSBUDDY_EAR_MAX_MSBUDDY_EAR_HANG_MSBUDDY_EAR_WAV_DIRBUDDY_SENSE_CAMERA_INDEXBUDDY_VISION_CAMERA_NAMEBUDDY_SENSE_FRAME_DIRBUDDY_VISION_EVENTS_LOG_MAX_BYTESBUDDY_VISION_FPSBUDDY_VISION_MOTIONBUDDY_VISION_MIN_LUMABUDDY_VISION_NOISE_WINDOWBUDDY_VISION_PERSON_BACKENDBUDDY_VISION_YOLO_MODELBUDDY_VISION_YOLO_CONFBUDDY_VISION_YOLO_IOUBUDDY_VISION_YOLO_DEVICEBUDDY_VISION_YOLO_CLASSESBUDDY_VISION_MAX_PERSONSBUDDY_VISION_TRACK_IOUBUDDY_VISION_MOTION_FRAME_SLOTSBUDDY_VISION_SEMANTIC_FRAME_SLOTSBUDDY_VISION_PERSON_LOST_SECSBUDDY_VISION_HEARTBEAT_SECSBUDDY_VISION_CAMERA_FAILURE_GRACEBUDDY_VISION_MOTION_EVENT_SECSBUDDY_VISION_BLINKBUDDY_VISION_DROWSY_SECSBUDDY_VISION_DETECTORSBUDDY_VISION_OBSERVATION_SECSOPENROUTER_API_KEYCODEBUDDY_FLEET_TOKENRANKLOCAL_RANKCUDA_VISIBLE_DEVICESCODEBUDDY_GPU_MAX_TEMP_CCODEBUDDY_GPU_JOB_RESULTCODEBUDDY_GPU_ALLOWED_ROOTS_JSONCODEBUDDY_PANOWORLD_COMMITCODEBUDDY_PANOWORLD_CANCEL_GRACE_SECONDSCODEBUDDY_PANOWORLD_ROOTHF_HOMEINFLUENCER_WORKDIRCOMFYUI_URLBROLL_OUTBROLL_SIZEBROLL_QUALITYBROLL_LENGTHINFLUENCER_RSS_FEEDSINFLUENCER_RANKING_LIMITFLOW_PROJECT_IDFLUX_CKPTFLUX_CLIP_LFLUX_T5FLUX_VAEPEXELS_API_KEYGMI_API_KEYGROK_IMAGINE_LOGGROK_IMAGINE_REFRESHGROK_IMAGINE_POLL_ATTEMPTSGROK_IMAGINE_POLL_INTERVALGROK_IMAGINE_BACKUPVIDEO_FONTVIDEO_MUSICVIDEO_NO_MUSICHEYGEN_API_KEYVEILLE_YOUTUBE_MODELVEILLE_YOUTUBE_ENGINEVEILLE_YOUTUBE_COOKIESVEILLE_YOUTUBE_COOKIES_FROM_BROWSEROMNIROUTE_ROOTNVIDIA_BASE_URLNVIDIA_API_KEYCODEBUDDY_QA_NODERECETTE_QA_BASECODEBUDDY_SESSIONS_DIRRECETTE_RESUME_IDCODEBUDDY_ELEVENLABS_MONTHLY_CAPPORTSENTRY_DSNDependencies
51 runtime dependencies (27 dev), 1 flagged: playwright-core
Tool inputs are validated
16/25 tool handlers declare input schemas (64%)
Declare an inputSchema with zod/joi/yup on every tool definition.
No access to sensitive paths
Reads sensitive paths: ~/.codebuddy/media.env, ~/.codebuddy/media.env, ~/.codebuddy/media.env
Remove reads of sensitive system paths. If you genuinely need them, document why in the README.
Shell command execution
4 calls in production code run through a shell (src/action/index.ts:84, src/doctor/index.ts:86, src/doctor/index.ts:518)
Prefer library functions over shell-outs. If you must shell out, ensure all inputs are properly escaped.
Dependency freshness
3/51 production deps abandoned (no release in 2+ years): diff-match-patch@2022-06-15 (4.3y), cli-highlight@2023-04-12 (3.4y), @iarna/toml@2023-07-15 (3.2y)
Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.
[](https://m8ven.ai/mcp/phuetz/code-buddy)?variant=verified from the URL.Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.
https://m8ven.ai/api/mcp/tool-check